Introduction to multimodal AI: capabilities, limits and what's next
This event has already taken place.
Read the story: Multimodal AI - a world beyond LLMs →Teodora Vuković and Aref Farhadipour on what multimodal AI can actually read from how people move, speak and react: the capabilities, the limits, and what's next.
Multimodal models are currently at the forefront of AI. Understand how multimodal AI can be used to understand human behavior, from the people building and researching it directly: evolution, capabilities, limits, future directions and practical takeaways.
Teodora Vuković leads the Multimodal Technology Group at the University of Zurich, working on multimodal AI and research infrastructure. She is a founder of MOSAIC, a multimodal AI MedTech startup. Aref Farhadipour is a PhD student with industry experience at Agigo, specialising in training multimodal models, speech processing and identity recognition.
One talk, then the room takes it apart over a drink. 17:00 at Ship26, on the Limmat in Zürich's old town.